© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129980
    Prev
    Next
    INDEX
    Explanations

    anger and harshness

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on words that describe an irritable, annoyed, or cranky mood (i.e. negative affect terms signaling annoyance or grumpiness).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gestalten
    -1.44
    欧阳
    -1.38
    u
    -1.31
    zieży
    -1.29
    叶子
    -1.27
    tigem
    -1.25
     entwickeln
    -1.23
    n
    -1.22
     ”
    -1.21
    Distinct
    -1.20
    POSITIVE LOGITS
    kontak
    1.45
     vijf
    1.41
     decisione
    1.38
     and
    1.37
     digunakan
    1.36
     cependant
    1.36
     posled
    1.34
     aveva
    1.32
    )
    1.32
     assholes
    1.31
    Activations Density 0.021%

    No Known Activations